augmented_model_fast_1

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2517
• Accuracy: 0.5608
• F1: 0.5595
• Precision: 0.5647
• Recall: 0.5598

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.7102	0.3133	500	0.7155	0.7212	0.7043	0.7161	0.7095
0.6079	0.6266	1000	0.7175	0.7260	0.7162	0.7241	0.7175
0.5849	0.9398	1500	0.7145	0.7321	0.7212	0.7293	0.7229
0.5017	1.2531	2000	0.7619	0.7295	0.7181	0.7230	0.7204
0.479	1.5664	2500	0.7685	0.7286	0.7173	0.7226	0.7194
0.4618	1.8797	3000	0.7758	0.7312	0.7230	0.7253	0.7239

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1